Show simple item record

dc.contributor.authorOrengo, Hector Aen
dc.contributor.authorConesa, Francesc Cen
dc.contributor.authorGarcia-Molsosa, Arnauen
dc.contributor.authorLobo, Agustínen
dc.contributor.authorGreen, Adamen
dc.contributor.authorMadella, Marcoen
dc.contributor.authorPetrie, Cameronen
dc.date.accessioned2020-07-06T23:31:19Z
dc.date.available2020-07-06T23:31:19Z
dc.date.issued2020-08en
dc.identifier.issn0027-8424
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/307675
dc.description.abstractThis paper presents an innovative multi-sensor, multi-temporal machine-learning approach using remote sensing Big Data for the detection of archaeological mounds in Cholistan (Pakistan). The Cholistan Desert presents one of the largest concentrations of Indus Civilisation sites from c. 3300 to 1500 BC). Cholistan has figured prominently in theories about changes in water availability, the rise and decline of the Indus Civilisation and the transformation of fertile monsoonal alluvial plains into an extremely arid margin. This paper implements the first archaeological application of a multi-sensor, multi-temporal machine learning approach for the remote detection of archaeological mounds. A classifier algorithm that employs a large-scale collection of Synthetic Aperture Radar and multispectral images has been implemented in Google Earth Engine, resulting in an accurate probability map for mound-like signatures across an area that covers c. 36,000 km2. The results show that the area presents many more archaeological mounds than previously recorded, extending south and east into the desert, which has major implications for understanding the archaeological significance of the region. The detection of new small (<5 ha) to large mounds (>30 ha) suggests that there were continuous shifts in settlement location. These shifts are likely to reflect responses to a dynamic and changing hydrological network and the influence of the progressive northward advance of the desert in a long-term process that culminated in the abandonment of much of the settled area during the Late Harappan period.
dc.description.sponsorshipERC
dc.format.mediumPrint-Electronicen
dc.languageengen
dc.publisherNational Academy of Sciences
dc.rightsAll rights reserved
dc.rights.uri
dc.titleAutomated detection of archaeological mounds using machine-learning classification of multisensor and multitemporal satellite data.en
dc.typeArticle
prism.endingPage18250
prism.issueIdentifier31en
prism.publicationDate2020en
prism.publicationNameProceedings of the National Academy of Sciences of the United States of Americaen
prism.startingPage18240
prism.volume117en
dc.identifier.doi10.17863/CAM.54768
dcterms.dateAccepted2020-06-23en
rioxxterms.versionofrecord10.1073/pnas.2005583117en
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2020-08en
dc.contributor.orcidOrengo, Hector A [0000-0002-9385-2370]
dc.contributor.orcidConesa, Francesc C [0000-0002-4026-7266]
dc.contributor.orcidGarcia-Molsosa, Arnau [0000-0001-5416-2986]
dc.contributor.orcidLobo, Agustín [0000-0002-6689-2908]
dc.contributor.orcidGreen, Adam [0000-0002-3324-5165]
dc.contributor.orcidMadella, Marco [0000-0002-9324-1545]
dc.contributor.orcidPetrie, Cameron [0000-0002-2926-7230]
dc.identifier.eissn1091-6490
rioxxterms.typeJournal Article/Reviewen
pubs.funder-project-idECH2020 EUROPEAN RESEARCH COUNCIL (ERC) (648609)
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) Marie Sk?odowska-Curie actions (746446)
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) Marie Sklodowska-Curie actions (794711)
pubs.funder-project-idBBSRC (BB/P027970/1)
cam.orpheus.successTue Jul 28 09:05:07 BST 2020 - Embargo updated*
cam.orpheus.counter2*
rioxxterms.freetoread.startdate2021-01-20


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record